A Parameter Update Balancing Algorithm for Multi-task Ranking Models in Recommendation Systems

TL;DR

This paper introduces PUB, a novel parameter update balancing algorithm for multi-task ranking models that improves performance across various scenarios and is effective in real-world industrial applications.

Contribution

PUB is the first method to optimize multi-task learning through parameter update balancing, addressing limitations of gradient-based approaches especially with momentum optimizers.

Findings

PUB improves multi-task ranking models on benchmark datasets.

PUB achieves state-of-the-art performance in multi-task learning.

PUB significantly enhances online ranking in a commercial platform.

Abstract

Multi-task ranking models have become essential for modern real-world recommendation systems. While most recommendation researches focus on designing sophisticated models for specific scenarios, achieving performance improvement for multi-task ranking models across various scenarios still remains a significant challenge. Training all tasks naively can result in inconsistent learning, highlighting the need for the development of multi-task optimization (MTO) methods to tackle this challenge. Conventional methods assume that the optimal joint gradient on shared parameters leads to optimal parameter updates. However, the actual update on model parameters may deviates significantly from gradients when using momentum based optimizers such as Adam, and we design and execute statistical experiments to support the observation. In this paper, we propose a novel Parameter Update Balancing algorithm for multi-task optimization, denoted as PUB. In contrast to traditional MTO method which are based on gradient level tasks fusion or loss level tasks fusion, PUB is the first work to optimize multiple tasks through parameter update balancing. Comprehensive experiments on benchmark multi-task ranking datasets demonstrate that PUB consistently improves several multi-task backbones and achieves state-of-the-art performance. Additionally, experiments on benchmark computer vision datasets show the great potential of PUB in various multi-task learning scenarios. Furthermore, we deployed our method for an industrial evaluation on the real-world commercial platform, HUAWEI AppGallery, where PUB significantly enhances the online multi-task ranking model, efficiently managing the primary traffic of a crucial channel.